Do Larger Models Really Win in Drug Discovery? A Benchmark Assessment of Model Scaling in AI-Driven Molecular Property and Activity Prediction

• URL: http://arxiv.org/abs/2604.26498v1
• Date: Wed, 29 Apr 2026 10:01:16 GMT
• Title: Do Larger Models Really Win in Drug Discovery? A Benchmark Assessment of Model Scaling in AI-Driven Molecular Property and Activity Prediction
• Abstract summary: We show that compact, specialized models remain highly effective for molecular property and activity prediction.<n>The performance differences among classical ML, GNN and pretrained sequence models are often modest and endpoint-dependent.<n>Results suggest that predictive performance depends on the alignment among molecular representation, inductive bias, data regime, endpoint biology and validation protocol.
• Score: 0.152292571922932
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The rapid growth of molecular foundation models and general-purpose large language models has encouraged a scale-centric view of artificial intelligence in drug discovery, in which larger pretrained models are expected to supersede compact cheminformatics models and task-specific graph neural networks (GNNs). We test this assumption on 22 molecular property and activity endpoints, including public ADMET and Tox21 benchmarks and two internal anti-infective activity datasets. Across 167,056 held-out task--molecule evaluations under structure-similarity-separated five-fold cross-validation (37,756 ADMET, 77,946 Tox21, 49,266 anti-TB and 2,088 antimalaria), classical machine-learning (ML) models such as RF(ECFP4) and ExtraTrees(RDKit descriptors) win ten primary-metric tasks, GNNs such as GIN and Ligandformer win nine, and pretrained molecular sequence models such as MoLFormer and ChemBERTa2 win three. Rule-based SAR reasoning baselines, represented by GPT5.5-SAR and Opus4.7-SAR, do not win under the prespecified primary metrics, although train-fold-derived SAR knowledge provides measurable but uneven gains for SAR reasoning and interpretation. These results indicate that compact, specialized models remain highly effective for molecular property and activity prediction. The performance differences among classical ML, GNN and pretrained sequence models are often modest and endpoint-dependent, whereas larger or more general models do not provide a universal predictive advantage. Large models may still add value for zero-shot reasoning, SAR interpretation and hypothesis generation, but the results suggest that predictive performance depends on the alignment among molecular representation, inductive bias, data regime, endpoint biology and validation protocol.

Related papers

• Investigating the Impact of Histopathological Foundation Models on Regressive Prediction of Homologous Recombination Deficiency [52.50039435394964]
  We systematically evaluate foundation models for regression-based tasks.<n>We extract patch-level features from whole slide images (WSI) using five state-of-the-art foundation models.<n>Models are trained to predict continuous HRD scores based on these extracted features across breast, endometrial, and lung cancer cohorts.
  arXiv  Detail & Related papers  (2026-01-29T14:06:50Z)
• Uncertainty-Guided Model Selection for Tabular Foundation Models in Biomolecule Efficacy Prediction [3.108481950101193]
  In this study, we investigate an uncertainty-guided strategy for model selection.<n>We show that a TabPFN model using straightforward sequence-based features can surpass specialized state-of-the-art predictors.
  arXiv  Detail & Related papers  (2025-10-02T18:33:19Z)
• Geometric Multi-color Message Passing Graph Neural Networks for Blood-brain Barrier Permeability Prediction [1.488392495573075]
  This paper introduces the geometric multi-color message-passing graph neural network (GMC-MPNN)<n>Our model constructs weighted colored subgraphs based on atom types to capture the spatial relationships and chemical context that govern blood-brain barrier permeability.
  arXiv  Detail & Related papers  (2025-07-25T03:38:46Z)
• UniGenX: a unified generative foundation model that couples sequence, structure and function to accelerate scientific design across proteins, molecules and materials [62.72989417755985]
  We present UniGenX, a unified generative model for function in natural systems.<n>UniGenX represents heterogeneous inputs as a mixed stream of symbolic and numeric tokens.<n>It achieves state-of-the-art or competitive performance for the function-aware generation across domains.
  arXiv  Detail & Related papers  (2025-03-09T16:43:07Z)
• CogDPM: Diffusion Probabilistic Models via Cognitive Predictive Coding [62.075029712357]
  This work introduces the Cognitive Diffusion Probabilistic Models (CogDPM) CogDPM features a precision estimation method based on the hierarchical sampling capabilities of diffusion models and weight the guidance with precision weights estimated by the inherent property of diffusion models. We apply CogDPM to real-world prediction tasks using the United Kindom precipitation and surface wind datasets.
  arXiv  Detail & Related papers  (2024-05-03T15:54:50Z)
• The Role of Model Architecture and Scale in Predicting Molecular Properties: Insights from Fine-Tuning RoBERTa, BART, and LLaMA [0.0]
  This study introduces a systematic framework to compare the efficacy of Large Language Models (LLMs) for fine-tuning across various cheminformatics tasks. We assessed three well-known models-RoBERTa, BART, and LLaMA-on their ability to predict molecular properties. We found that LLaMA-based models generally offered the lowest validation loss, suggesting their superior adaptability across tasks and scales.
  arXiv  Detail & Related papers  (2024-05-02T02:20:12Z)
• Bi-level Contrastive Learning for Knowledge-Enhanced Molecule Representations [68.32093648671496]
  We introduce GODE, which accounts for the dual-level structure inherent in molecules.<n> Molecules possess an intrinsic graph structure and simultaneously function as nodes within a broader molecular knowledge graph.<n>By pre-training two GNNs on different graph structures, GODE effectively fuses molecular structures with their corresponding knowledge graph substructures.
  arXiv  Detail & Related papers  (2023-06-02T15:49:45Z)
• Uni-QSAR: an Auto-ML Tool for Molecular Property Prediction [15.312021665242154]
  We propose Uni-QSAR, a powerful Auto-ML tool for molecule property prediction tasks. Uni-QSAR combines molecular representation learning (MRL) of 1D sequential tokens, 2D topology graphs, and 3D conformers with pretraining models to leverage rich representation from large-scale unlabeled data.
  arXiv  Detail & Related papers  (2023-04-24T16:29:08Z)
• Unraveling Key Elements Underlying Molecular Property Prediction: A Systematic Study [27.56700461408765]
  Key elements underlying molecular property prediction remain largely unexplored. We conduct an extensive evaluation of representative models using various representations on the MoleculeNet datasets. In total, we have trained 62,820 models, including 50,220 models on fixed representations, 4,200 models on SMILES sequences and 8,400 models on molecular graphs.
  arXiv  Detail & Related papers  (2022-09-26T14:07:59Z)
• Graph neural networks for the prediction of molecular structure-property relationships [59.11160990637615]
  Graph neural networks (GNNs) are a novel machine learning method that directly work on the molecular graph. GNNs allow to learn properties in an end-to-end fashion, thereby avoiding the need for informative descriptors. We describe the fundamentals of GNNs and demonstrate the application of GNNs via two examples for molecular property prediction.
  arXiv  Detail & Related papers  (2022-07-25T11:30:44Z)
• On the Generalization and Adaption Performance of Causal Models [99.64022680811281]
  Differentiable causal discovery has proposed to factorize the data generating process into a set of modules. We study the generalization and adaption performance of such modular neural causal models. Our analysis shows that the modular neural causal models outperform other models on both zero and few-shot adaptation in low data regimes.
  arXiv  Detail & Related papers  (2022-06-09T17:12:32Z)
• A multi-stage machine learning model on diagnosis of esophageal manometry [50.591267188664666]
  The framework includes deep-learning models at the swallow-level stage and feature-based machine learning models at the study-level stage. This is the first artificial-intelligence-style model to automatically predict CC diagnosis of HRM study from raw multi-swallow data.
  arXiv  Detail & Related papers  (2021-06-25T20:09:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.